Search: “research”

A Survey of Adversarial Efficiency Degradation for Vision Transformer by Exploiting Input-adaptive Optimization

arXiv:2608.05217v1 Announce Type: cross Abstract: Vision Transformers (ViTs) increasingly rely on input-adaptive inference, such as token pruning and early halting, to meet energy and latency budgets.

Research

A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition

DGX agent

arXiv:2608.05673v1 Announce Type: new Abstract: Trajectory prediction has shifted toward structured formulations with explicit social modeling. However, existing methods inadequately distinguish the f

researcharxiv-cs-ai

7 Aug 2026

ABC: Numerical Data Collection under Local Differential Privacy without Prior Knowledge

arXiv:2608.05737v1 Announce Type: cross Abstract: Local Differential Privacy (LDP) provides strong privacy guarantees for collecting numerical data. A fundamental challenge, however, is that existing

Active View Selection for Scene-level Multi-view Crowd Counting and Localization with Limited Labeling Budget

arXiv:2509.16684v2 Announce Type: replace Abstract: Multi-view crowd counting and localization fuse the input multi-views for estimating the crowd number or locations on the ground. Existing methods m

AegisShield: Democratizing Cyber Threat Modeling with Generative AI

arXiv:2509.10482v2 Announce Type: replace-cross Abstract: The increasing sophistication of technology systems makes traditional threat modeling hard to scale, especially for small organizations with l

An Inertial Block Proximal Linearized Method with Adaptive Momentum for Nonconvex and Nonsmooth Optimization

arXiv:2608.05502v1 Announce Type: cross Abstract: In this paper, we consider a class of multiblock nonconvex nonsmooth optimization problems, which covers many applications such as the analysis of pre

An Optimal Agnostic PAC Algorithm

arXiv:2608.06363v1 Announce Type: cross Abstract: Let Hsubseteq{-1,+1}^X be a class of finite VC dimension dge1. Writing L for the binary risk and L^*=min_{hin H}L(h), we construct a learner achieving

Answer First, Reason Later: Commitment Order in Diffusion LLMs

arXiv:2608.05687v1 Announce Type: cross Abstract: Masked diffusion language models (dLLMs) can commit tokens in any order -- a freedom marketed as their core advantage over autoregressive decoding. We

Automatic Detection of Deaths from Social Networking Sites

arXiv:2608.05183v1 Announce Type: cross Abstract: This dissertation analysed and discussed the differences in linguistic characteristics between pre-mortem and post-mortem social media content, and re

BaKron: Efficient Quantization with Kronecker-Factored Hessians

arXiv:2608.06291v1 Announce Type: cross Abstract: We accelerate a family of algorithms for neural network quantization whose geometry is informed by any Kronecker-factored approximation of the Hessian

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks

arXiv:2608.05926v1 Announce Type: cross Abstract: Edge inference is a promising paradigm to provide large language model (LLM) inference services in next-generation mobile networks. LLM inference main

Bayesian adaptively-weighted ensembles for few-shot abdominal segmentation

arXiv:2608.05815v1 Announce Type: new Abstract: Few-shot learning has emerged as a promising approach for anatomical segmentation when labelled data are scarce. However, different few-shot learning al

Bayesian Expected Uncertainty Reduction (B-EUR) Model: A Computational Account of What Makes Design Options Worth Trying

arXiv:2608.05642v1 Announce Type: new Abstract: This paper proposes the Bayesian Expected Uncertainty Reduction (B-EUR) model, which formalizes the value of trying a candidate design action as its exp

Behavioral Residualization for Unsupervised Intrusion Detection in Automotive CAN Networks

arXiv:2608.05548v1 Announce Type: cross Abstract: Modern vehicles rely on the Controller Area Network (CAN) bus, whose design prioritizes low cost and real-time performance but provides no message aut

BendTwin: Robust Dense-to-Sparse Physical Reconstruction with Bending-Aware Differentiable Spring-Mass Models

arXiv:2608.06164v1 Announce Type: new Abstract: Reconstructing objects with mechanical properties from video observations enables physically consistent dynamic prediction, benefiting robotics planning

Berkeley and Heiserman as an Unexhausted Architecture for Embodied Machine Intelligence

arXiv:2607.16465v2 Announce Type: replace Abstract: Edmund C. Berkeley is usually remembered as a mediator between symbolic logic and early computing, yet that standard description understates the sco

Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation

arXiv:2608.05999v1 Announce Type: new Abstract: Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models. H

researcharxiv-cs-ro

Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs

arXiv:2608.05592v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong progress in video understanding, yet it remains challenging because the token limitation m

Beyond Information Retrieval: Generative AI as an Epistemic Arbiter to Enhance Collaborative Problem-Solving

arXiv:2608.05171v1 Announce Type: cross Abstract: Generative AI (GAI) creates new opportunities for collaborative problem-solving (CPS), yet its role in shaping student interaction remains unclear. To

🚨 BREAKING — Anthropic investors worry Dario Amodei’s AI doom marketing could hurt its upcoming IPO. “He’s more of a religious leader than …

🚨 BREAKING — Anthropic investors worry Dario Amodei’s AI doom marketing could hurt its upcoming IPO. “He’s more of a religious leader than he is a CEO.” > used to write sensitive OpenAI memos on an of

researchyann-lecun--x

CDSeg: A Renderable Gaussian Carrier for Image-to-3D Label Transfer

arXiv:2608.05482v1 Announce Type: new Abstract: Modern image models provide strong cues about what should be segmented in each view, but their masks do not by themselves determine where those labels s

CFGPNet: Cross-Attention-Based Fused Gradient Programmed Network Framework for Multispectral Object Detection

arXiv:2608.06205v1 Announce Type: new Abstract: RGB--T object detection exploits the complementary strengths of visible and infrared imagery, supporting robust perception in low-light, adverse-weather

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

arXiv:2603.08652v2 Announce Type: replace Abstract: Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integra

Coherence-Oriented Dream Scene Visualisation

arXiv:2608.05233v1 Announce Type: new Abstract: Dreams can be emotionally intense but difficult to communicate. We describe the Dream Scene Visualiser (DSV) system which turns written dream descriptio

CohortHijack: Robustness of Single Cell Annotation to Companion Cell Removal

arXiv:2608.05900v1 Announce Type: new Abstract: Many single-cell annotation tools refine an initial cell label using nearby cells or cluster-level voting. We study whether this refinement can be manip

Confidence matters: Leveraging Multi-view Geometric Priors for GS-based Reconstruction

arXiv:2608.06117v1 Announce Type: new Abstract: 3D Gaussian splatting (3DGS) has emerged as a widely-used tool for novel view synthesis, offering real-time rendering in a sparse representation. Howeve

Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading

arXiv:2608.05675v1 Announce Type: new Abstract: Label-free reliability for vision-language models rests on invariance: perturb the input and a faithful reader's answer should not change. This has a kn

Constraint-First Reasoning: A Training-Free Protocol for Exploiting Answer-Space Constraints in Mathematical Problem Solving

arXiv:2608.05254v1 Announce Type: new Abstract: Large language models can derive a plausible mathematical object yet still violate explicit requirements--for example, by omitting a modular reduction,

Context Matters: Support Set Selection and Failure Detection for In-Context Medical Image Segmentation

arXiv:2608.05333v1 Announce Type: new Abstract: In-context learning (ICL) adapts medical image segmentation models to unseen structures and modalities without retraining by conditioning on a task-spec

Controllable Clothing: Precise Labels and Generation for Virtual Try-On with Latent Diffusion Models

arXiv:2608.05834v1 Announce Type: new Abstract: In this technical report, I present a new method for guiding image generation in the context of Virtual- Try-On (VITON). The proposed method leverages n

Coordinated Multi-Robot Disassembly for Makespan Optimization of Large-Scale Assemblies

arXiv:2608.05830v1 Announce Type: new Abstract: Multi-robot task and motion planning for disassembly tasks requires robots to operate in confined workspaces while coordinating their motions with other

researcharxiv-cs-ro

Counterfactual Analysis via Large Language Models

arXiv:2608.05367v1 Announce Type: new Abstract: Counterfactual analysis aims to predict potential outcomes under hypothetical scenarios, offering valuable insights for decision-making. This paper inve

CPC-CMS: Cognitive Pairwise Comparison Classification Model Selection Framework for Document-level Sentiment Analysis

arXiv:2507.14022v2 Announce Type: replace Abstract: This study proposes the Cognitive Pairwise Comparison Classification Model Selection (CPC-CMS) framework for document-level sentiment analysis. The

d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation

arXiv:2601.07568v3 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-orde

DBLAST: Dependent Block Drafting for Stochastic Speculative Decoding

arXiv:2608.05448v1 Announce Type: new Abstract: Speculative decoding accelerates large language models' inference by using a lightweight drafter to propose multiple future tokens and a target model to

Decomposed Entailment for Factuality Checking and Hallucination Detection

arXiv:2608.05823v1 Announce Type: new Abstract: The reliability of Large Language Models (LLMs) is often compromised by factual inconsistencies, including hallucinations---cases where generated conten

Dense-Cast: A lightweight ensemble of deep learning architectures for precipitation nowcasting

arXiv:2608.06082v1 Announce Type: new Abstract: Proper short-term forecasting of precipitation is crucial in disaster management and preparedness. Nonetheless, the variability and nonlinearity of prec

Diff-VF: Training-free High-quality Long Video Generation via Diffusion Model

arXiv:2608.05976v1 Announce Type: new Abstract: Recently, diffusion models have made great progress in video generation. However, most existing video diffusion models are trained with short videos, an

Discrete energy as an exact label-free training objective for finite-element surrogates

arXiv:2608.05437v1 Announce Type: cross Abstract: Supervised training of finite-element (FE) surrogate models requires reference solutions, and each reference solution is obtained by solving the syste

Does FLAIR super-resolution erase or hallucinate small white-matter lesions?

arXiv:2608.06311v1 Announce Type: cross Abstract: White matter hyperintensities (WMH), bright regions on Fluid-attenuated Inversion Recovery (FLAIR) scans are associated with cerebrovascular pathology

Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping

arXiv:2608.05626v1 Announce Type: new Abstract: We propose DOME-HDR, a dual-output multi-exposure HDR reconstruction framework that jointly produces a perceptually balanced SDR image and a consistent

Engram-E2VID: Reference-Based Event-to-Video Reconstruction via Generative Activation of Appearance Engrams

arXiv:2608.05728v1 Announce Type: new Abstract: Reference-based event-to-video reconstruction aims to recover target RGB frames from a reference frame and the event stream captured over the reference-

EqDeepRx: Learning a Scalable and Interference Mitigating MIMO Receiver

arXiv:2602.11834v2 Announce Type: replace-cross Abstract: While machine learning (ML)-based receiver algorithms have received a great deal of attention in the recent literature, they often suffer from

Equipment-centric workpiece localization in near real-time using deep learning-based vision and event-driven finite state machines

arXiv:2608.05744v1 Announce Type: new Abstract: Continuous workpiece localization is essential for traceability and process coordination in hot forging, but direct tracking is unreliable because of ex

Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction

arXiv:2608.05265v1 Announce Type: cross Abstract: Prediction of post-wildfire debris flows is critical for mitigating hazards to communities, infrastructure, and resources during intense rainfall in r

Example-Guided Prompting for Document-Level Text Simplification

arXiv:2608.05447v1 Announce Type: new Abstract: Document-level text simplification requires large language models (LLMs) to rewrite complex documents while preserving meaning, readability, and discour

Flow-Map Distillation on Relation Manifolds for Image Restoration

arXiv:2608.05769v1 Announce Type: new Abstract: Knowledge distillation for image restoration typically aligns intermediate features or relation matrices between teacher and student networks as static

From Continuous Predictors to Clinical Thresholds: Early Evidence on Performance Trade-offs of Guideline-Based Categorisation for Ischaemic Stroke Outcome Prediction

arXiv:2608.05203v1 Announce Type: new Abstract: Machine learning models achieve strong predictive accuracy for 90-day outcome prediction in acute ischaemic stroke, yet clinical adoption is limited by